5,321
edits
Convolutional neural network: Difference between revisions
→Padding
| Line 69: | Line 69: | ||
===Padding=== | ===Padding=== | ||
Convolutional layers yield an output smaller than the input size. | Convolutional layers typically yield an output smaller than the input size. | ||
We can use padding to increase the input size. | We can use padding to increase the input size. | ||
See [https://www.machinecurve.com/index.php/2020/02/10/using-constant-padding-reflection-padding-and-replication-padding-with-keras/ Machinecurve: Using Constant Padding, Reflection Padding and Replication Padding with Keras] | See [https://www.machinecurve.com/index.php/2020/02/10/using-constant-padding-reflection-padding-and-replication-padding-with-keras/ Machinecurve: Using Constant Padding, Reflection Padding and Replication Padding with Keras] | ||